---
title: "Gemini 3.1 Flash-Lite — API access"
description: "Gemini 3.1 Flash-Lite API pricing: official $0.25/$1.50 per 1M tokens, $0.125/$0.75 with the flat 50% apiToken.sale discount. The economical Gemini 3 tier."
url: "https://apitoken.sale/models/gemini-3-1-flash-lite"
language: "en"
---
# Gemini 3.1 Flash-Lite

Gemini 3.1 Flash-Lite is the economical tier of the Gemini 3 line — built for high-volume, latency-sensitive work at a fraction of Flash pricing.

- **Model ID:** `gemini-3.1-flash-lite`
- **Tier:** Flash-Lite
- **Context window:** 1M tokens
- **Max output:** 64K tokens
- **Official price (per 1M):** $0.25 input / $1.5 output
- **Your price (per 1M):** input $0.125, output $0.75 (flat 50% off)
- **Base URL:** `https://gemini.api.apitoken.sale` · **Endpoint:** `POST /v1beta/models/gemini-3.1-flash-lite:generateContent` (x-goog-api-key)

## Best for

- Classification, extraction and summarization at scale.
- Latency-sensitive chat and routing layers.
- Cheap pre-processing before a Flash or Pro call.

## Notes

- Cached input bills at 10% of input ($0.025 per 1M); caching is automatic on repeated prefixes.
- Full 1M-token context and 64K max output — the same window as the Flash line.

## Call it

```bash
curl https://gemini.api.apitoken.sale/v1beta/models/gemini-3.1-flash-lite:generateContent \
  -H "x-goog-api-key: $APITOKEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"contents": [{"parts": [{"text": "Reply with exactly: connected"}]}]}'
```

## FAQ

**How much does the Gemini 3.1 Flash-Lite API cost?**

Officially $0.25 per 1M input tokens and $1.50 per 1M output tokens, with cached input at $0.025. With the flat 50% apiToken.sale discount that is $0.125/$0.75.

**What is the model ID?**

gemini-3.1-flash-lite. Point any Gemini-compatible client at https://gemini.api.apitoken.sale and send it as the model, with the key in x-goog-api-key.

**Flash-Lite or Flash?**

Flash-Lite handles bulk, latency-sensitive work at a fraction of the price; step up to gemini-3.6-flash for agentic coding and harder reasoning. Many teams route by task on the same key.

---
API reference: https://apitoken.sale/md/docs · All models: https://apitoken.sale/md/models